I’m not very good at drawing, but when I went to grad school and class was boring, I would make lots of random doodles in my notebooks. Since V4 is so good with image prompts, I have been photographing them and seeing how AI can evolve the silly little sketches.
I love how it interprets some, adding style and objects and color, but keeping the main elements. It’s cool too because it adds another layer of creative input to the fairly automated process.
I think people look at AI as being too machine-driven, and it kind of is at times, but little things like this let the user gain more control. I foresee a future of AI where we can use sketches, draw over an image to alter it, and create multiple prompts for certain areas of the image. It’s going to be a wild tool, and one that will take a lot of learning and work as well. ✏
(click the prompt to copy it!)
/imagine prompt: IMAGEURL a drawing of a man climbing a staircase that leads to the moon, 3d elements, an open book, insanely detailed with psychedelic color, hard lighting --ar 2:3 --stylize 1000 --chaos 100 --v 4
/imagine prompt: IMAGEURL a colorful painting --v 4 --ar 2:3
(click to view)